Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 46858
    Prev
    Next
    INDEX
    Explanations

    initial, original

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raci
    -0.07
     واقعی
    -0.06
    ียว
    -0.06
     가까
    -0.06
    //{↵
    -0.06
    equalsIgnoreCase
    -0.06
     dalla
    -0.06
     plc
    -0.06
    zens
    -0.06
    buch
    -0.06
    POSITIVE LOGITS
     crossAxisAlignment
    0.06
    暂
    0.06
    Informe
    0.06
    .ignore
    0.06
    mix
    0.06
     cover
    0.06
    �
    0.06
    .BorderSize
    0.06
     suites
    0.06
     William
    0.06
    Activations Density 0.039%

    No Known Activations